Siraj Raval has a video explaining the Unity and it’s new AI tool.
Creating 3D AI in a simulated world is actually pretty easy using Unity. It’s a powerful tool and I’ll go over its new ML Agents toolkit, that allows researchers and developers to build/train ML models in a 3D simulation. It’s pretty fun watching it in a 3D world, lets break down the code and concepts.
Recently, Andy and I had a chance to chat with Amanda Lange, technology evangelist at Microsoft, games journalist, and data aficionado.
Press the play button below to listen here or visit the show page at DataDriven.tv
- Frank is working on a Wintellect on Azure Gov (1:30)
- Amanda’s site is Second Truth.com (99:00)
- The psychology of games (5:30)
- Movie reference: Back to the Future (6:30)
- How an Apple Watch or FitBit knows you’re asleep (7:10)
- Game violence activates sections of the brain (but it’s short-lived) (8:30)
- Andy lives in Farmville-not-the-game (10:30)
- Zynga and A/B testing (10:45)
- Amanda plays a lot of Overwatch these days (11:30)
- “Games as a Service” (12:10)
- Psychology in games Jeffrey “Lyte” Lin on Shaping Behavior in Online Games (13:30)
- Amanda writes for Tap Repeatedly (15:00)
- Amanda loves teaching people! (17:10)
- “I wasn’t a data scientist until I was.” (17:50)
- On privacy and data… (19:00)
- Berkeley’s Data Science curriculum is online (19:40)
- Learn data science at Data 8 (22:15)
- GLaDOS is a character in the Portal games (25:00)
- The orchestral version of Still Alive (28:00)
- No arm-wrestling with Amanda (31:45)
- “We can learn anything.” (32:45)
- Trapping a self-driving car using salt… (34:00)
- Ready Player One audio book (35:40)
- Ready Player One, the Movie (99:00)
- The Adventure Zone (37:50)
- Audible (get a free book!) has the Dragonlance series (39:25)
- Amanda tried out for American Idol (41:00)
- Amanda’s on Twitter @second_truth (42:00)
For the next 10 weeks Siraj Raval is going to go from the basics to the state of the art of reinforcement learning (RL), a popular subfield of machine learning using video game environments as our testbed.
RL is a huge reason DeepMind and OpenAI have been so successful thus far in creating world changing AI bots.
- Code for this video: https://github.com/llSourcell/AI_for_video_games_demo
- Course Syllabus: https://github.com/llSourcell/AI_for_Video_Games_Syllabus